© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3337
    Prev
    Next
    INDEX
    Explanations

    say "identity"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     componente
    -17.75
     treat
    -16.50
    (component
    -16.13
    зд
    -16.13
    _section
    -15.88
     section
    -15.38
    -course
    -15.19
    section
    -14.94
    sections
    -14.88
    работать
    -14.75
    POSITIVE LOGITS
     identity
    49.00
    身份
    47.00
     Identity
    44.75
    identity
    44.00
    Identity
    41.50
    的身份
    35.75
    _identity
    35.25
    .identity
    35.00
    (identity
    32.50
     identities
    31.50
    Activations Density 0.081%

    No Known Activations